© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196890
    Prev
    Next
    INDEX
    Explanations

    un-treatable or great

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ਰ
    0.95
    -
    0.92
    IAN
    0.86
     overlook
    0.85
    0.85
    การ
    0.84
    ม
    0.83
     comer
    0.82
    ue
    0.79
     overlooking
    0.79
    POSITIVE LOGITS
    f
    1.03
    c
    0.88
    g
    0.83
     Володи
    0.79
     Бре
    0.78
     Шу
    0.77
     Васи
    0.73
    faf
    0.72
    h
    0.72
     Де
    0.71
    Activations Density 0.000%

    No Known Activations